Date:	Mon, 16 Mar 2015 11:37:58 -0700
From:	"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
To:	linux-kernel@...r.kernel.org
Cc:	mingo@...nel.org, laijs@...fujitsu.com, dipankar@...ibm.com,
	akpm@...ux-foundation.org, mathieu.desnoyers@...icios.com,
	josh@...htriplett.org, tglx@...utronix.de, peterz@...radead.org,
	rostedt@...dmis.org, dhowells@...hat.com, edumazet@...gle.com,
	dvhart@...ux.intel.com, fweisbec@...il.com, oleg@...hat.com,
	bobby.prani@...il.com,
	"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Subject: [PATCH v2 tip/core/rcu 14/22] rcu: Move rcu_report_unblock_qs_rnp() to common code

From: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>

The rcu_report_unblock_qs_rnp() function is invoked when the
last task blocking the current grace period exits its outermost
RCU read-side critical section.  Previously, this was called only
from rcu_read_unlock_special(), and was therefore defined only when
CONFIG_RCU_PREEMPT=y.  However, this function will be invoked even when
CONFIG_RCU_PREEMPT=n once CPU-hotplug operations are processed only at
the beginnings of RCU grace periods.  The reason for this change is that
the last task on a given leaf rcu_node structure's ->blkd_tasks list
might well exit its RCU read-side critical section between the time that
recent CPU-hotplug operations were applied and when the new grace period
was initialized.  This situation could result in RCU waiting forever on
that leaf rcu_node structure, because if all that structure's CPUs were
already offline, there would be no quiescent-state events to drive that
structure's part of the grace period.

This commit therefore moves rcu_report_unblock_qs_rnp() to common code
that is built unconditionally so that the quiescent-state-forcing code
can clean up after this situation, avoiding the grace-period stall.

Signed-off-by: Paul E. McKenney <paulmck@...ux.vnet.ibm.com>
---
 kernel/rcu/tree.c        | 39 +++++++++++++++++++++++++++++++++++++++
 kernel/rcu/tree_plugin.h | 40 ++--------------------------------------
 2 files changed, 41 insertions(+), 38 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a7151d26b940..5b5cb1ff73ed 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2127,6 +2127,45 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 }
 
 /*
+ * Record a quiescent state for all tasks that were previously queued
+ * on the specified rcu_node structure and that were blocking the current
+ * RCU grace period.  The caller must hold the specified rnp->lock with
+ * irqs disabled, and this lock is released upon return, but irqs remain
+ * disabled.
+ */
+static void __maybe_unused rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
+				      struct rcu_node *rnp, unsigned long flags)
+	__releases(rnp->lock)
+{
+	unsigned long mask;
+	struct rcu_node *rnp_p;
+
+	WARN_ON_ONCE(rsp == &rcu_bh_state || rsp == &rcu_sched_state);
+	if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		return;  /* Still need more quiescent states! */
+	}
+
+	rnp_p = rnp->parent;
+	if (rnp_p == NULL) {
+		/*
+		 * Either there is only one rcu_node in the tree,
+		 * or tasks were kicked up to root rcu_node due to
+		 * CPUs going offline.
+		 */
+		rcu_report_qs_rsp(rsp, flags);
+		return;
+	}
+
+	/* Report up the rest of the hierarchy. */
+	mask = rnp->grpmask;
+	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
+	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
+	smp_mb__after_unlock_lock();
+	rcu_report_qs_rnp(mask, rsp, rnp_p, flags);
+}
+
+/*
  * Record a quiescent state for the specified CPU to that CPU's rcu_data
  * structure.  This must be either called from the specified CPU, or
  * called when the specified CPU is known to be offline (and when it is
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index a22721547442..ec6c2efb28cd 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -233,43 +233,6 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 }
 
 /*
- * Record a quiescent state for all tasks that were previously queued
- * on the specified rcu_node structure and that were blocking the current
- * RCU grace period.  The caller must hold the specified rnp->lock with
- * irqs disabled, and this lock is released upon return, but irqs remain
- * disabled.
- */
-static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
-	__releases(rnp->lock)
-{
-	unsigned long mask;
-	struct rcu_node *rnp_p;
-
-	if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		return;  /* Still need more quiescent states! */
-	}
-
-	rnp_p = rnp->parent;
-	if (rnp_p == NULL) {
-		/*
-		 * Either there is only one rcu_node in the tree,
-		 * or tasks were kicked up to root rcu_node due to
-		 * CPUs going offline.
-		 */
-		rcu_report_qs_rsp(&rcu_preempt_state, flags);
-		return;
-	}
-
-	/* Report up the rest of the hierarchy. */
-	mask = rnp->grpmask;
-	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
-	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
-	smp_mb__after_unlock_lock();
-	rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
-}
-
-/*
  * Advance a ->blkd_tasks-list pointer to the next entry, instead
  * returning NULL if at the end of the list.
  */
@@ -399,7 +362,8 @@ void rcu_read_unlock_special(struct task_struct *t)
 							 rnp->grplo,
 							 rnp->grphi,
 							 !!rnp->gp_tasks);
-			rcu_report_unblock_qs_rnp(rnp, flags);
+			rcu_report_unblock_qs_rnp(&rcu_preempt_state,
+						  rnp, flags);
 		} else {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		}
-- 
1.8.1.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists